BlockRun MCP
MCP server giving AI agents live data — markets, crypto, research, X — billed per call via x402 micropayments.
Last release Jul 28, 2026 · Last commit Jul 30, 2026 · ★ 477
Overview
MCP server giving AI agents live data — markets, crypto, research, X — billed per call via x402 micropayments.
Sato Score
86/100· HighHow open, active & verifiable — not a safety or returns grade.
- Maintenance & liveness
- 35/35
- Code transparency
- 19/20
- Interface verifiability
- 8/10
- Docs & demo
- 6/10
- Listing transparency & provenance
- 14/15
- Independent verification
- 4/10
Deploy path reproduced — install verified in an isolated container (proves installability, not runtime safety).
Details
- Chains
- Base, Solana
- Agent types
- MCP, Data
- Open source
- Yes
- Pricing
- Pay-per-call in USDC via x402. Market queries from $0.001, Exa searches $0.01/query, image gen from $0.015, video from $0.05/sec. $5 USDC ≈ 5,000 market queries or 500 Exa searches.
- Last checked
- 2026-07-31
Marketplace Signals
No marketplace signals recorded for this resource yet.
Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.
Where BlockRun MCP fits
Related concepts: How Agents Use Wallets, What Are Onchain Agents?, What Are MCPs? The Standard Way to Give Agents Tools
Recent Activity
All news →Releases and posts from BlockRun MCP, pulled from its GitHub and X.
blockrun-mcp v0.33.0 — a read-only Polymarket tool, effect-based safety annotations, and pre-payment validation
A 20th tool, MCP safety annotations that describe effect instead of price, and pre-payment request validation ( #81 ). feat(polymarket) — blockrun_polymarket_read , a read-only companion tool. positions , orders , and a live CLOB preview that builds real order economics from the book but has no confirm input and cannot sign or submit. blockrun_polymarket keeps every action for compatibility, but m
blockrun-mcp v0.32.9 — close the external-review backlog: withdraw double-spend window, USDC.e sweep, and six more
Closes the external-review backlog: all 8 findings from the Kimi K3 review ( #72 ) and both unabsorbed pieces of @KillerQueen-Z 's #59 / #66 ( #71 ). fix(polymarket) — the withdraw retry double-spend window is closed ( #72 .1). The relayer SDK's wait() polls 200s and returns undefined for BOTH an on-chain failure and a timeout, while the signed batch stays executable until its 300s deadline — and
blockrun-mcp v0.32.8 — paid chat calls stream, so slow reasoning models stop 524ing after payment
Paid chat calls now stream. A non-streaming request to a slow reasoning model (Kimi K3 with a large prompt generates for minutes) moves ZERO bytes between "request accepted" and "body ready", so the edge in front of the gateway kills the idle connection at ~100s and returns 524 — AFTER the x402 payment settled. Charged, nothing delivered. Observed live 2026-07-21, twice. fix(chat) — paid EVM paths
blockrun-mcp v0.32.3 — nine audit findings, including one in 0.32.2's own headline fix
A multi-agent audit of 0.32.2 across nine angles, every finding put through two independent skeptics. It caught nine real defects — including one in 0.32.2's own headline fix. The nastiest is not a money bug: an optional dependency could kill the entire server. fix(server) — a missing sharp took down all 19 tools. sharp is an optionalDependency , but inline-image.ts imported it at the top level, s
blockrun-mcp v0.32.2 — the free tier throws away everything past 128 KiB and returns 200 as if it hadn't
Two leftovers from the #61 review, both settled with measurements. The free tier truncates silently at 128 KiB usage.prompt_tokens is the only tell, and it flatlines: sent prompt_tokens 110,000 B 22,065 125,000 B 25,065 130,000 B 26,065 135,000 B 26,266 ← capped 150,000 B 26,266 ← identical, 15 KB discarded Identical on gpt-oss-120b and deepseek-v4-flash , so this is a property of the free path ,
blockrun-mcp 0.31.6 — a dead skill, a phantom endpoint, and a live price gate
Two of these were live the whole time and invisible to every prior audit round: a skill that never loaded and an endpoint that never existed . Both were found by asking the gateway instead of re-reading our own files. prediction-markets has never once loaded Its description read ...you CANNOT get from a public API: historical price... . A plain YAML scalar may not contain ": " , so the frontmatter
Listing History
Recorded changes to BlockRun MCP's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.
- Jul 28, 2026New release published
- Jul 27, 2026Verified: deploy spec
- Jul 21, 2026New release published
- Jul 14, 2026Enriched: risk level
- Jun 25, 2026Enriched: pricing, marketplace notes
- Jun 25, 2026Auto-enriched: tags, creator name, agent type
- Jun 22, 2026Auto-enriched: docs url, website url, supported integrations, chains supported +3 more
- Jun 22, 2026Sato Score tier: Medium → HighScore 65 → 79.
- Jun 18, 202611 releases trackedShowing the 2 most recent. Full release history is retained in the listing record.
- Jun 17, 2026Sato Score tier: Low → MediumScore 33 → 65.
Related Resources
Zerion
ActiveWallet and DeFi data provider offering portfolio, positions, transactions, PnL, and prices across many chains, with an agent-accessible API.
Agent Payments Protocol (AP2)
ActiveOpen protocol from Google for secure agent-led payments across traditional and crypto rails, with a crypto-native x402 extension built with Coinbase, Ethereum Foundation, and MetaMask.
Bankr
ActiveCrypto execution layer and cross-chain wallet that lets agents and users trade, bridge, and manage assets via natural language, plus a skills marketplace and an x402 cloud for spinning up pay-per-call agent endpoints.
Join the Sato Hub Briefing
One email a week — the agents, tools, and infrastructure that actually shipped, and why they matter.